library(tidyverse)
[30m── [1mAttaching packages[22m ───────────────────────────────────────────────────────────────────────────────────────── tidyverse 1.2.1 ──[39m
[30m[32m✔[30m [34mggplot2[30m 3.0.0 [32m✔[30m [34mpurrr [30m 0.2.5
[32m✔[30m [34mtibble [30m 1.4.2 [32m✔[30m [34mdplyr [30m 0.7.6
[32m✔[30m [34mtidyr [30m 0.8.1 [32m✔[30m [34mstringr[30m 1.3.1
[32m✔[30m [34mreadr [30m 1.1.1 [32m✔[30m [34mforcats[30m 0.3.0[39m
[30m── [1mConflicts[22m ──────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
[31m✖[30m [34mdplyr[30m::[32mfilter()[30m masks [34mstats[30m::filter()
[31m✖[30m [34mdplyr[30m::[32mlag()[30m masks [34mstats[30m::lag()[39m
library(lubridate)
Attaching package: ‘lubridate’
The following object is masked from ‘package:base’:
date
I - Introduction
II - Data Preprocessing
Load datasets
dt_issues = read.csv("data/issues_data.csv", header=TRUE)
dt_star = read.csv("data/stargazers.csv", header=TRUE)
dt_user = read.csv("data/users_data.csv", header=TRUE)
Saniety Check
# Inspect the dataset by taking the first 10 rows of each dataset.
dt_issues %>% head(10)
dt_star %>% head(10)
dt_user %>% head(10)